Assessment of melanoma thickness based on dermoscopy images: an open, web-based, international, diagnostic study.

BACKGROUND: Preoperative assessment of whether a melanoma is invasive or in situ (MIS) is a common task that might have important implications for triage, prognosis and the selection of surgical margins. Several dermoscopic features suggestive of melanoma have been described, but only a few of these are useful in differentiating MIS from invasive melanoma. OBJECTIVE: The primary aim of this study was to evaluate how accurately a large number of international readers, individually as well as collectively, were able to discriminate between MIS and invasive melanomas as well as estimate the Breslow thickness of invasive melanomas based on dermoscopy images. The secondary aim was to compare the accuracy of two machine learning convolutional neural networks (CNNs) and the collective reader response. METHODS: We conducted an open, web-based, international, diagnostic reader study using an online platform. The online challenge opened on 10 May 2021 and closed on 19 July 2021 (71 days) and was advertised through several social media channels. The investigation included, 1456 dermoscopy images of melanomas (788 MIS; 474 melanomas ≤1.0 mm and 194 >1.0 mm). A test set comprising 277 MIS and 246 invasive melanomas was used to compare readers and CNNs. RESULTS: We analysed 22 314 readings by 438 international readers. The overall accuracy (95% confidence interval) for melanoma thickness was 56.4% (55.7%-57.0%), 63.4% (62.5%-64.2%) for MIS and 71.0% (70.3%-72.1%) for invasive melanoma. Readers accurately predicted the thickness in 85.9% (85.4%-86.4%) of melanomas ≤1.0 mm (including MIS) and in 70.8% (69.2%-72.5%) of melanomas >1.0 mm. The reader collective outperformed a de novo CNN but not a pretrained CNN in differentiating MIS from invasive melanoma. CONCLUSIONS: Using dermoscopy images, readers and CNNs predict melanoma thickness with fair to moderate accuracy. Readers most accurately discriminated between thin (≤1.0 mm including MIS) and thick melanomas (>1.0 mm).

Position paper on a simplified histopathological classification of basal cell carcinoma: results of the European Consensus Project.

BACKGROUND: Histopathological classification of basal cell carcinoma (BCC) has important prognostic and therapeutic implications, but reproducibility of BCC subtyping among dermatopathologists is poor. OBJECTIVES: To obtain a consensus paper on BCC classification and subtype definitions. METHODS: A panel of 12 recognized dermatopathologists (G12) from nine European countries used a modified Delphi method and evaluated 100 BCC cases uploaded to a website. The strategy involved five steps: (I) agreement on definitions for WHO 2018 BCC subtypes; (II) classification of 100 BCCs using the agreed definitions; (III) discussion on the weak points of the WHO classification and proposal of a new classification with clinical insights; (IV) re-evaluation of the 100 BCCs using the new classification; and (V) external independent evaluation by 10 experienced dermatopathologists (G10). RESULTS: A simplified classification unifying infiltrating, sclerosing, and micronodular BCCs into a single "infiltrative BCC" subtype improved reproducibility and was practical from a clinical standpoint. Fleiss' κ values increased for all subtypes, and the level of agreement improved from fair to moderate for the nodular and the unified infiltrative BCC groups, respectively. The agreement for basosquamous cell carcinoma remained fair, but κ values increased from 0.276 to 0.342. The results were similar for the G10 group. Delphi consensus was not achieved for the concept of trichoblastic carcinoma. In histopathological reports of BCC displaying multiple subtypes, only the most aggressive subtype should be mentioned, except superficial BCC involving margins. CONCLUSIONS: The three BCC subtypes with infiltrative growth pattern, characteristically associated with higher risk of deep involvement (infiltrating, sclerosing, and micronodular), should be unified in a single group. The concise and encompassing term "infiltrative BCCs" can be used for these tumors. A binary classification of BCC into low-risk and high-risk subtypes on histopathological grounds alone is questionable; correlation with clinical factors is necessary to determine BCC risk and therapeutic approach.

Perilesional sun damage as a diagnostic clue for pigmented actinic keratosis and Bowen's disease.

BACKGROUND: Chronic sun damage in the background is common in pigmented actinic keratoses and Bowen's disease (pAK/BD). While explainable artificial intelligence (AI) demonstrated increased background attention for pAK/BD, humans frequently miss this clue in dermatoscopic images because they tend to focus on the lesion. AIM: To analyse whether perilesional sun damage is a robust diagnostic clue for pAK/BD and if teaching this clue to dermatoscopy users improves their diagnostic accuracy. METHODS: We assessed the interrater agreement and the frequency of perilesional sun damage in 220 dermatoscopic images and conducted a reader study with 124 dermatoscopy users. The readers were randomly assigned to one of two online tutorials; one tutorial pointed to perilesional sun damage as a clue to pAK/BD (group A) the other did not (group B). In both groups, we compared the frequencies of correct diagnoses before and after receiving the tutorial. RESULTS: The frequency of perilesional sun damage was higher in pAK/BD than in other types of pigmented skin lesions and interrater agreement was good (kappa = 0.675). The diagnostic accuracy for pAK/BD improved in both groups of readers (group A: +16.1%, 95%-CI: 9.5-22.7; group B: +13.1%; 95%-CI: 7.1-19.0; P for both <0.001), but the overall accuracy improved only in group A from (59.1% (95%-CI: 55.0-63.1) to 63.5% (95%-CI: 59.5-67.6); P = 0.002). CONCLUSION: Perilesional sun damage is a good clue to differentiate pAK/BD from other pigmented skin lesions in dermatoscopic images, which could be useful for teledermatology. Knowledge of this clue improves the accuracy of dermatoscopy users, which demonstrates that insights from explainable AI can be used to train humans.

Single-cell RNA sequencing profiling in a patient with discordant primary cutaneous B-cell and T-cell lymphoma reveals micromilieu-driven immune skewing.

BACKGROUND: Primary cutaneous lymphomas comprise a heterogeneous group of B-cell and T-cell malignancies which often show an indolent course, but can progress to aggressive disease in a subset of patients. Diagnosis is often delayed owing to clinical and histopathological similarities with benign inflammatory conditions. Especially during early disease, cancer cells are present at relatively low percentages compared with the inflammatory infiltrate, an interplay that is currently only insufficiently understood. OBJECTIVES: To improve diagnostics and perform molecular characterization of a complex type of primary cutaneous lymphoma. METHODS: Single-cell RNA sequencing (scRNA-seq) was performed and combined with T-cell and B-cell receptor sequencing. RESULTS: We were able to diagnose a patient with concurrent mycosis fungoides (MF) and primary cutaneous follicle centre lymphoma (PCFCL), appearing in mutually exclusive skin lesions. Profiling of tumour cells and the tissue microenvironment revealed a type-2 immune skewing in MF, most likely guided by the expanded clone that also harboured upregulation of numerous pro-oncogenic genes. By contrast, PCFCL lesions exhibited a more type-1 immune phenotype, consistent with its indolent behaviour. CONCLUSIONS: These data not only illustrate the diagnostic potential of scRNA-seq, but also allow the characterization of specific clonal populations that shape the unique tissue microenvironment in clinically distinct types of lymphoma skin lesions.

Dermatoscopy of combined blue nevi: a multicentre study of the International Dermoscopy Society.

BACKGROUND: Combined blue nevi (CBN) may mimic melanoma and are relatively often biopsied for diagnostic reasons. OBJECTIVE: To better characterize CBN and to compare it with melanoma. METHODS: We collected clinical and dermatoscopic images of 111 histologically confirmed CBN and contrasted their dermatoscopic characteristics with 132 partly blue coloured melanomas. Furthermore, we compared the accuracy of human experts using pattern analysis with a computer algorithm based on deep learning. RESULTS: Combined blue nevi are usually flat or slightly elevated and, in comparison with melanoma, more frequent on the head and neck. Dermatoscopically, they are typified by a blue structureless part in combination with either brown clods (n = 52, 46.8%), lines (n = 28, 25.2%) or skin-coloured or brown structureless areas (n = 31, 27.9%). In contrast with melanoma, the blue part of CBN is more often well defined (18.9% vs. 4.5%, P < 0.001) and more often located in the centre (22.5% vs. 5.3%, P < 0.001). Melanomas are more often chaotic (OR: 28.7, 95% CI: 14.8-55.7, P < 0.001), have at least one melanoma clue (OR: 10.8, 95% CI: 5.2-22.2 P < 0.001) in particular white lines (OR: 37.1, 95% CI: 13.4-102.9, P < 0.001). Using simplified pattern analysis (chaos and clues), two raters reached sensitivities of 93.9% (95% CI: 88.4-97.3%) and 92.4% (95% CI: 86.5-96.3%) at corresponding specificities of 59.5% (95% CI: 49.7-68.7%) and 65.8% (95% CI: 56.2-74.5%). The human accuracy with pattern analysis was on par with a state-of-the-art computer algorithm based on deep learning that achieved an area under the curve of (0.92, 95% CI: 0.87-0.96) and a specificity of 85.3% (95% CI: 76.5-91.7%) at a given sensitivity of 83.6% (95% CI: 72.5-91.5%). CONCLUSION: CBN usually lack melanoma clues, in particular white lines. The accuracy of pattern analysis for combined nevi is acceptable, and histopathologic confirmation may not be necessary in exemplary cases.

Human surface anatomy terminology for dermatology: a Delphi consensus from the International Skin Imaging Collaboration.

BACKGROUND: There is no internationally vetted set of anatomic terms to describe human surface anatomy. OBJECTIVE: To establish expert consensus on a standardized set of terms that describe clinically relevant human surface anatomy. METHODS: We conducted a Delphi consensus on surface anatomy terminology between July 2017 and July 2019. The initial survey included 385 anatomic terms, organized in seven levels of hierarchy. If agreement exceeded the 75% established threshold, the term was considered 'accepted' and included in the final list. Terms added by the participants were passed on to the next round of consensus. Terms with <75% agreement were included in subsequent surveys along with alternative terms proposed by participants until agreement was reached on all terms. RESULTS: The Delphi included 21 participants. We found consensus (≥75% agreement) on 361/385 (93.8%) terms and eliminated one term in the first round. Of 49 new terms suggested by participants, 45 were added via consensus. To adjust for a recently published International Classification of Diseases-Surface Topography list of terms, a third survey including 111 discrepant terms was sent to participants. Finally, a total of 513 terms reached agreement via the Delphi method. CONCLUSIONS: We have established a set of 513 clinically relevant terms for denoting human surface anatomy, towards the use of standardized terminology in dermatologic documentation.

[Artificial intelligence and smartphone program applications (Apps) : Relevance for dermatological practice]. / Künstliche Intelligenz und Smartphone-Programm-Applikationen (Apps) : Bedeutung für die dermatologische Praxis.

ADVANTAGES OF ARTIFICIAL INTELLIGENCE (AI): With responsible, safe and successful use of artificial intelligence (AI), possible advantages in the field of dermato-oncology include the following: (1) medical work can focus on skin cancer patients, (2) patients can be more quickly and effectively treated despite the increasing incidence of skin cancer and the decreasing number of actively working dermatologists and (3) users can learn from the AI results. POTENTIAL DISADVANTAGES AND RISKS OF AI USE: (1) Lack of mutual trust can develop due to the decreased patient-physician contact, (2) additional time effort will be necessary to promptly evaluate the AI-classified benign lesions, (3) lack of adequate medical experience to recognize misclassified AI decisions and (4) recontacting a patient in due time in the case of incorrect AI classifications. Still problematic in the use of AI are the medicolegal situation and remuneration. Apps using AI currently cannot provide sufficient assistance based on clinical images of skin cancer. REQUIREMENTS AND POSSIBLE USE OF SMARTPHONE PROGRAM APPLICATIONS: Smartphone program applications (apps) can be implemented responsibly when the image quality is good, the patient's history can be entered easily, transmission of the image and results are assured and medicolegal aspects as well as remuneration are clarified. Apps can be used for disease-specific information material and can optimize patient care by using teledermatology.

Man against machine reloaded: performance of a market-approved convolutional neural network in classifying a broad spectrum of skin lesions in comparison with 96 dermatologists working under less artificial conditions.

BACKGROUND: Convolutional neural networks (CNNs) efficiently differentiate skin lesions by image analysis. Studies comparing a market-approved CNN in a broad range of diagnoses to dermatologists working under less artificial conditions are lacking. MATERIALS AND METHODS: One hundred cases of pigmented/non-pigmented skin cancers and benign lesions were used for a two-level reader study in 96 dermatologists (level I: dermoscopy only; level II: clinical close-up images, dermoscopy, and textual information). Additionally, dermoscopic images were classified by a CNN approved for the European market as a medical device (Moleanalyzer Pro, FotoFinder Systems, Bad Birnbach, Germany). Primary endpoints were the sensitivity and specificity of the CNN's dichotomous classification in comparison with the dermatologists' management decisions. Secondary endpoints included the dermatologists' diagnostic decisions, their performance according to their level of experience, and the CNN's area under the curve (AUC) of receiver operating characteristics (ROC). RESULTS: The CNN revealed a sensitivity, specificity, and ROC AUC with corresponding 95% confidence intervals (CI) of 95.0% (95% CI 83.5% to 98.6%), 76.7% (95% CI 64.6% to 85.6%), and 0.918 (95% CI 0.866-0.970), respectively. In level I, the dermatologists' management decisions showed a mean sensitivity and specificity of 89.0% (95% CI 87.4% to 90.6%) and 80.7% (95% CI 78.8% to 82.6%). With level II information, the sensitivity significantly improved to 94.1% (95% CI 93.1% to 95.1%; P < 0.001), while the specificity remained unchanged at 80.4% (95% CI 78.4% to 82.4%; P = 0.97). When fixing the CNN's specificity at the mean specificity of the dermatologists' management decision in level II (80.4%), the CNN's sensitivity was almost equal to that of human raters, at 95% (95% CI 83.5% to 98.6%) versus 94.1% (95% CI 93.1% to 95.1%); P = 0.1. In contrast, dermatologists were outperformed by the CNN in their level I management decisions and level I and II diagnostic decisions. More experienced dermatologists frequently surpassed the CNN's performance. CONCLUSIONS: Under less artificial conditions and in a broader spectrum of diagnoses, the CNN and most dermatologists performed on the same level. Dermatologists are trained to integrate information from a range of sources rendering comparative studies that are solely based on one single case image inadequate.

Standardization of dermoscopic terminology and basic dermoscopic parameters to evaluate in general dermatology (non-neoplastic dermatoses): an expert consensus on behalf of the International Dermoscopy Society.

BACKGROUND: Over the last few years, several articles on dermoscopy of non-neoplastic dermatoses have been published, yet there is poor consistency in the terminology among different studies. OBJECTIVES: We aimed to standardize the dermoscopic terminology and identify basic parameters to evaluate in non-neoplastic dermatoses through an expert consensus. METHODS: The modified Delphi method was followed, with two phases: (i) identification of a list of possible items based on a systematic literature review and (ii) selection of parameters by a panel of experts through a three-step iterative procedure (blinded e-mail interaction in rounds 1 and 3 and a face-to-face meeting in round 2). Initial panellists were recruited via e-mail from all over the world based on their expertise on dermoscopy of non-neoplastic dermatoses. RESULTS: Twenty-four international experts took part in all rounds of the consensus and 13 further international participants were also involved in round 2. Five standardized basic parameters were identified: (i) vessels (including morphology and distribution); (ii) scales (including colour and distribution); (iii) follicular findings; (iv) 'other structures' (including colour and morphology); and (v) 'specific clues'. For each of them, possible variables were selected, with a total of 31 different subitems reaching agreement at the end of the consensus (all of the 29 proposed initially plus two more added in the course of the consensus procedure). CONCLUSIONS: This expert consensus provides a set of standardized basic dermoscopic parameters to follow when evaluating inflammatory, infiltrative and infectious dermatoses. This tool, if adopted by clinicians and researchers in this field, is likely to enhance the reproducibility and comparability of existing and future research findings and uniformly expand the universal knowledge on dermoscopy in general dermatology. What's already known about this topic? Over the last few years, several papers have been published attempting to describe the dermoscopic features of non-neoplastic dermatoses, yet there is poor consistency in the terminology among different studies. What does this study add? The present expert consensus provides a set of standardized basic dermoscopic parameters to follow when evaluating inflammatory, infiltrative and infectious dermatoses. This consensus should enhance the reproducibility and comparability of existing and future research findings and uniformly expand the universal knowledge on dermoscopy in general dermatology.

Dermoscopic features of mammary Paget's disease: a retrospective case-control study by the International Dermoscopy Society.

BACKGROUND: Mammary Paget's disease (MPD) is a rare intraepidermal adenocarcinoma of the nipple-areola complex, associated with an underlying breast cancer in approximately 90% of cases. Delayed diagnosis of MPD is common. Its dermoscopic features have been ill defined in the literature. OBJECTIVES: To determine the clinical and dermoscopic features of MPD versus other dermatologic entities that involve nipple and areola. METHODS: Members of the IDS were invited to submit any case of histologically confirmed MPD, as well as other benign and malignant dermatoses that involve the nipple and areola complex. A standardized evaluation of the dermoscopic images was performed and the results were statistically analyzed. RESULTS: Sixty-five lesions were included in the study, 22 (33.8%) of them MPD and 43 (66.2%) controls. The most frequent dermoscopic criteria of MPD were white scales (86.4%) and pink structureless areas (81.8%), followed by dotted vessels (72.7%), erosion/ulceration (68.2%) and white shiny lines (63.6%). The multivariate analysis showed that white scales and pink structureless areas were significant predictors of MPD, posing a 68-fold and a 31-fold probability of MPD, respectively. Split of the population into pigmented and non-pigmented lesions showed that in pigmented MPD, pink structureless areas, white lines and grey granules and dots are positive predictors of the disease. Among non-pigmented lesions, pink structureless areas, white lines, erosion/ulceration and white scales served as predictors of MPD. CONCLUSIONS: The most frequent profile of an individual with MPD is an elderly female with unilateral, asymptomatic, erythematous plaque of the nipple, dermoscopically displaying pink structureless areas, fine white scales, dotted and a few short linear vessels. In case of pigmentation we may also observe brown structureless areas and pigmented granules. LIMITATIONS: Small sample size, retrospective design.

Diagnostic accuracy of content-based dermatoscopic image retrieval with deep classification features.

BACKGROUND: Automated classification of medical images through neural networks can reach high accuracy rates but lacks interpretability. OBJECTIVES: To compare the diagnostic accuracy obtained by using content-based image retrieval (CBIR) to retrieve visually similar dermatoscopic images with corresponding disease labels against predictions made by a neural network. METHODS: A neural network was trained to predict disease classes on dermatoscopic images from three retrospectively collected image datasets containing 888, 2750 and 16 691 images, respectively. Diagnosis predictions were made based on the most commonly occurring diagnosis in visually similar images, or based on the top-1 class prediction of the softmax output from the network. Outcome measures were area under the receiver operating characteristic curve (AUC) for predicting a malignant lesion, multiclass-accuracy and mean average precision (mAP), measured on unseen test images of the corresponding dataset. RESULTS: In all three datasets the skin cancer predictions from CBIR (evaluating the 16 most similar images) showed AUC values similar to softmax predictions (0·842, 0·806 and 0·852 vs. 0·830, 0·810 and 0·847, respectively; P > 0·99 for all). Similarly, the multiclass-accuracy of CBIR was comparable with softmax predictions. Compared with softmax predictions, networks trained for detecting only three classes performed better on a dataset with eight classes when using CBIR (mAP 0·184 vs. 0·368 and 0·198 vs. 0·403, respectively). CONCLUSIONS: Presenting visually similar images based on features from a neural network shows comparable accuracy with the softmax probability-based diagnoses of convolutional neural networks. CBIR may be more helpful than a softmax classifier in improving diagnostic accuracy of clinicians in a routine clinical setting.

[Image-based computer diagnosis of melanoma]. / Bildbasierte Computerdiagnose des Melanoms.

The use of automated diagnostic systems for the diagnosis of melanomas is becoming increasingly more established. These are based on the following four steps: 1) preprocessing, to ensure that disturbing factors are eliminated, 2) segmentation, the separation of the image and the background, 3) extraction and selection of features that provide the highest measure of accuracy for the diagnosis and 4) classification, in which the lesion is assigned to a diagnostic class. Recently, the computer-assisted diagnosis of melanoma has focused on algorithms based on transfer learning, which can make steps 2 and 3 obsolete and provides better results. In this article we also review smartphone applications in the field of melanoma screening and recognition. These applications should be considered with caution as they are available to lay persons although the diagnostic accuracy of these applications has not usually been tested in clinical trials.

[Dermoscopy for malignant and benign skin tumors : Indication and standardized terminology]. / Dermatoskopie bei malignen und benignen Hauttumoren : Indikation und standardisierte Terminologie.

Dermoscopy has a high diagnostic accuracy in pigmented and nonpigmented malignant and benign skin tumors. These microscopic in vivo examinations with polarized and nonpolarized light are effective in the early detection of malignant skin tumors and reduce the number of unnecessary excisions of benign skin tumors. The selection of the skin lesions is crucial for the diagnostic accuracy of the dermoscopic examination. Not only large pigmented skin lesions, but also small hypo-, de-, or nonpigmented skin lesions, should be examined dermatoscopically as well as skin lesions that have changed in shape and/or color. In clinical routine, research and teaching, the dermoscopic diagnosis should be performed by describing the visible structures, their distribution and colors by means of descriptive and/or metaphoric terminology. Optionally, a diagnostic algorithm can also be used. Especially in benign lesions, the dermatoscopic diagnosis should be uniform for the complete area. Comparison with other nearby skin tumors of the same patient (comparative approach) is helpful in the evaluation of numerous melanocytic skin tumors. If it is unclear whether the lesion is malignant, a biopsy or complete excision should be performed with subsequent histopathological examination.

The impact of dermoscopy on melanoma detection in the practice of dermatologists in Europe: results of a pan-European survey.

BACKGROUND: Dermoscopy is a widely used technique that can increase the sensitivity and specificity of melanoma detection. Information is lacking on the impact of dermoscopy use on the detection of melanoma in the real-life practice of European dermatologists. OBJECTIVE: To identify factors that influence the benefit of using dermoscopy for increasing melanoma detection and lowering the number of unnecessary biopsies in the practice of European dermatologists. METHODS: We conducted a survey of dermatologists registered in 32 European countries regarding the following: the demographic and practice characteristics, dermoscopy training and use, opinions on dermoscopy and the self-estimated impact of dermoscopy use on the number of melanomas detected and the number of unnecessary biopsies performed in practice. RESULTS: Valid answers were collected for 7480 respondents, of which 6602 reported using dermoscopy. Eighty-six per cent of dermoscopy users reported that dermoscopy increased the numbers of melanomas they detected, and 70% reported that dermoscopy decreased the number of unnecessary biopsies of benign lesions they performed. The dermatologists reporting these benefits were more likely to have received dermoscopy training during residency, to use dermoscopy frequently and intensively, and to use digital dermoscopy systems and pattern analysis compared to dermatologists who did not perceive any benefit of dermoscopy for the melanoma recognition in their practice. CONCLUSIONS: Improving dermoscopy training, especially during residency and increasing access to digital dermoscopy equipment are important paths to enhance the benefit of dermoscopy for melanoma detection in the practice of European dermatologists.